Meta-learning-based percussion transcription and $t\bar{a}la$ identification from low-resource audio

This study introduces a meta-learning-based approach for low-resource Tabla Stroke Transcription (TST) and $t\bar{a}la$ identification in Hindustani classical music. Using Model-Agnostic Meta-Learning (MAML), we address the challenge of limited annotated datasets, enabling rapid adaptation to new tasks with minimal data. The method is validated across various datasets, including tabla solo and concert recordings, demonstrating robustness in polyphonic audio scenarios. We propose two novel $t\bar{a}la$ identification techniques based on stroke sequences and rhythmic patterns. Additionally, the approach proves effective for Automatic Drum Transcription (ADT), showcasing its flexibility for Indian and Western percussion music. Experimental results show that the proposed method outperforms existing techniques in low-resource settings, significantly contributing to music transcription and studying musical traditions through computational tools.

Dementia Detection using Multi-modal Methods on Audio Data

Dementia is a neurodegenerative disease that causes gradual cognitive impairment, which is very common in the world and undergoes a lot of research every year to prevent and cure it. It severely impacts the patient's ability to remember events and communicate clearly, where most variations of it have no known cure, but early detection can help alleviate symptoms before they become worse. One of the main symptoms of dementia is difficulty in expressing ideas through speech. This paper attempts to talk about a model developed to predict the onset of the disease using audio recordings from patients. An ASR-based model was developed that generates transcripts from the audio files using Whisper model and then applies RoBERTa regression model to generate an MMSE score for the patient. This score can be used to predict the extent to which the cognitive ability of a patient has been affected. We use the PROCESS_V1 dataset for this task, which is introduced through the PROCESS Grand Challenge 2025. The model achieved an RMSE score of 2.6911 which is around 10 percent lower than the described baseline.

Novel Class Discovery for Open Set Raga Classification

The task of Raga classification in Indian Art Music (IAM) is constrained by the limited availability of labeled datasets, resulting in many Ragas being unrepresented during the training of machine learning models. Traditional Raga classification methods rely on supervised learning, and assume that for a test audio to be classified by a Raga classification model, it must have been represented in the training data, which limits their effectiveness in real-world scenarios where novel, unseen Ragas may appear. To address this limitation, we propose a method based on Novel Class Discovery (NCD) to detect and classify previously unseen Ragas. Our approach utilizes a feature extractor trained in a supervised manner to generate embeddings, which are then employed within a contrastive learning framework for self-supervised training, enabling the identification of previously unseen Raga classes. The results demonstrate that the proposed method can accurately detect audio samples corresponding to these novel Ragas, offering a robust solution for utilizing the vast amount of unlabeled music data available online. This approach reduces the need for manual labeling while expanding the repertoire of recognized Ragas, and other music data in Music Information Retrieval (MIR).

BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection

Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that encodes speech into discrete, speaker-agnostic semantic tokens. This facilitates fast retrieval using text-based search algorithms and effectively handles out-of-vocabulary terms. Our approach focuses on generating consistent token sequences across varying utterances of the same term. We also propose a bidirectional state space modeling within the Mamba encoder, trained in a self-supervised learning framework, to learn contextual frame-level features that are further encoded into discrete tokens. Our analysis shows that our speech tokens exhibit greater speaker invariance than those from existing tokenizers, making them more suitable for STD tasks. Empirical evaluation on LibriSpeech and TIMIT databases indicates that our method outperforms existing STD baselines while being more efficient.

$T\bar{a}laGen:$ A System for Automatic $T\bar{a}la$ Identification and Generation

In Hindustani classical music, the tabla plays an important role as a rhythmic backbone and accompaniment. In applications like computer-based music analysis, learning singing, and learning musical instruments, tabla stroke transcription, $t\bar{a}la$ identification, and generation are crucial. This paper proposes a comprehensive system aimed at addressing these challenges. For tabla stroke transcription, we propose a novel approach based on model-agnostic meta-learning (MAML) that facilitates the accurate identification of tabla strokes using minimal data. Leveraging these transcriptions, the system introduces two novel $t\bar{a}la$ identification methods based on the sequence analysis of tabla strokes. \par Furthermore, the paper proposes a framework for $t\bar{a}la$ generation to bridge traditional and modern learning methods. This framework utilizes finite state transducers (FST) and linear time-invariant (LTI) filters to generate $t\bar{a}las$ with real-time tempo control through user interaction, enhancing practice sessions and musical education. Experimental evaluations on tabla solo and concert datasets demonstrate the system's exceptional performance on real-world data and its ability to outperform existing methods. Additionally, the proposed $t\bar{a}la$ identification methods surpass state-of-the-art techniques. The contributions of this paper include a combined approach to tabla stroke transcription, innovative $t\bar{a}la$ identification techniques, and a robust framework for $t\bar{a}la$ generation that handles the rhythmic complexities of Hindustani music.

Explainable Deep Learning Analysis for Raga Identification in Indian Art Music

The task of Raga Identification is a very popular research problem in Music Information Retrieval. Few studies that have explored this task employed various approaches, such as signal processing, Machine Learning (ML) methods, and more recently Deep Learning (DL) based methods. However, a key question remains unanswered in all of these works: do these ML/DL methods learn and interpret Ragas in a manner similar to human experts? Besides, a significant roadblock in this research is the unavailability of ample supply of rich, labeled datasets, which drives these ML/DL based methods. In this paper, we introduce "Prasarbharti Indian Music" version-1 (PIM-v1), a novel dataset comprising of 191 hours of meticulously labeled Hindustani Classical Music (HCM) recordings, which is the largest labeled dataset for HCM recordings to the best of our knowledge. Our approach involves conducting ablation studies to find the benchmark classification model for Automatic Raga Identification (ARI) using PIM-v1 dataset. We achieve a chunk-wise f1-score of 0.89 for a subset of 12 Raga classes. Subsequently, we employ model explainability techniques to evaluate the classifier's predictions, aiming to ascertain whether they align with human understanding of Ragas or are driven by arbitrary patterns. We validate the correctness of model's predictions by comparing the explanations given by two ExAI models with human expert annotations. Following this, we analyze explanations for individual test examples to understand the role of regions highlighted by explanations in correct or incorrect predictions made by the model.

Outlier Robust Multivariate Polynomial Regression

We study the problem of robust multivariate polynomial regression: let $p\colon\mathbb{R}^n\to\mathbb{R}$ be an unknown $n$-variate polynomial of degree at most $d$ in each variable. We are given as input a set of random samples $(\mathbf{x}_i,y_i) \in [-1,1]^n \times \mathbb{R}$ that are noisy versions of $(\mathbf{x}_i,p(\mathbf{x}_i))$. More precisely, each $\mathbf{x}_i$ is sampled independently from some distribution $\chi$ on $[-1,1]^n$, and for each $i$ independently, $y_i$ is arbitrary (i.e., an outlier) with probability at most $\rho < 1/2$, and otherwise satisfies $|y_i-p(\mathbf{x}_i)|\leq\sigma$. The goal is to output a polynomial $\hat{p}$, of degree at most $d$ in each variable, within an $\ell_\infty$-distance of at most $O(\sigma)$ from $p$. Kane, Karmalkar, and Price [FOCS'17] solved this problem for $n=1$. We generalize their results to the $n$-variate setting, showing an algorithm that achieves a sample complexity of $O_n(d^n\log d)$, where the hidden constant depends on $n$, if $\chi$ is the $n$-dimensional Chebyshev distribution. The sample complexity is $O_n(d^{2n}\log d)$, if the samples are drawn from the uniform distribution instead. The approximation error is guaranteed to be at most $O(\sigma)$, and the run-time depends on $\log(1/\sigma)$. In the setting where each $\mathbf{x}_i$ and $y_i$ are known up to $N$ bits of precision, the run-time's dependence on $N$ is linear. We also show that our sample complexities are optimal in terms of $d^n$. Furthermore, we show that it is possible to have the run-time be independent of $1/\sigma$, at the cost of a higher sample complexity.

Interactive singing melody extraction based on active adaptation

Extraction of predominant pitch from polyphonic audio is one of the fundamental tasks in the field of music information retrieval and computational musicology. To accomplish this task using machine learning, a large amount of labeled audio data is required to train the model. However, a classical model pre-trained on data from one domain (source), e.g., songs of a particular singer or genre, may not perform comparatively well in extracting melody from other domains (target). The performance of such models can be boosted by adapting the model using very little annotated data from the target domain. In this work, we propose an efficient interactive melody adaptation method. Our method selects the regions in the target audio that require human annotation using a confidence criterion based on normalized true class probability. The annotations are used by the model to adapt itself to the target domain using meta-learning. Our method also provides a novel meta-learning approach that handles class imbalance, i.e., a few representative samples from a few classes are available for adaptation in the target domain. Experimental results show that the proposed method outperforms other adaptive melody extraction baselines. The proposed method is model-agnostic and hence can be applied to other non-adaptive melody extraction models to boost their performance. Also, we released a Hindustani Alankaar and Raga (HAR) dataset containing 523 audio files of about 6.86 hours of duration intended for singing melody extraction tasks.

AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning

Deep generative models complement Markov-chain-Monte-Carlo methods for efficiently sampling from high-dimensional distributions. Among these methods, explicit generators, such as Normalising Flows (NFs), in combination with the Metropolis Hastings algorithm have been extensively applied to get unbiased samples from target distributions. We systematically study central problems in conditional NFs, such as high variance, mode collapse and data efficiency. We propose adversarial training for NFs to ameliorate these problems. Experiments are conducted with low-dimensional synthetic datasets and XY spin models in two spatial dimensions.

TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASR

Confidence estimation of predictions from an End-to-End (E2E) Automatic Speech Recognition (ASR) model benefits ASR's downstream and upstream tasks. Class-probability-based confidence scores do not accurately represent the quality of overconfident ASR predictions. An ancillary Confidence Estimation Model (CEM) calibrates the predictions. State-of-the-art (SOTA) solutions use binary target scores for CEM training. However, the binary labels do not reveal the granular information of predicted words, such as temporal alignment between reference and hypothesis and whether the predicted word is entirely incorrect or contains spelling errors. Addressing this issue, we propose a novel Temporal-Lexeme Similarity (TeLeS) confidence score to train CEM. To address the data imbalance of target scores while training CEM, we use shrinkage loss to focus on hard-to-learn data points and minimise the impact of easily learned data points. We conduct experiments with ASR models trained in three languages, namely Hindi, Tamil, and Kannada, with varying training data sizes. Experiments show that TeLeS generalises well across domains. To demonstrate the applicability of the proposed method, we formulate a TeLeS-based Acquisition (TeLeS-A) function for sampling uncertainty in active learning. We observe a significant reduction in the Word Error Rate (WER) as compared to SOTA methods.